Title | ||
---|---|---|
Recurrent Neural Network Based Small-Footprint Wake-Up-Word Speech Recognition System With A Score Calibration Method |
Abstract | ||
---|---|---|
In this paper, we propose a small-footprint wake-up-word speech recognition (WUWSR) system based on long short-term memory (LSTM) recurrent neural network, and we design a novel back-end calibration scoring method named modified zero normalization (MZN). First, LSTM is trained to predict posterior probability of context-dependent state. Next, MZN is adopted to transfer posterior probability to normalized score, which is then converted to confidence score by dynamic programming. Finally, a certain wake-up-word is recognized according to the confidence score. This WUWSR system can recognize multiple wake-up words and change wake-up words flexibly. This system can guarantee low latency by omitting decoding network. Equal error rate (EER) is adopted as the evaluation metric. Experimental results show that the proposed LSTM-based system achieves 33.33% relative improvement compared with a baseline system based on deep feed-forward neural network. Combining the front-end LSTM acoustic model with back-end MZN method, our WUWSR system can achieve 51.92% relative improvement. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/ICPR.2018.8546063 | 2018 24TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR) |
Keywords | Field | DocType |
wake-up word speech recognition, LSTM, modified zero normalization, dynamic programming search | Normalization (statistics),Pattern recognition,Computer science,Word error rate,Recurrent neural network,Speech recognition,Posterior probability,Artificial intelligence,Decoding methods,Artificial neural network,Hidden Markov model,Acoustic model | Conference |
ISSN | Citations | PageRank |
1051-4651 | 0 | 0.34 |
References | Authors | |
0 | 5 |